MAI-Voice-2.1
Text-to-speech model from Microsoft. One API key reaches this provider and every other model in the catalog.
No card required. Start with 1 million free tokens.
About MAI-Voice-2.1
MAI-Voice-2.1 is a text-to-speech model published by Microsoft. Through TrustedRouter it runs on 1 provider, with options in the US, from $23.21/M characters.
- Model ID
microsoft/mai-voice-2.1- Publisher
- Microsoft
- Input limit
- 5000 characters
- Input price
- $23.21/M characters
- Formats
- pcm, mp3
- Voices
- en-US-Harper, en-US-Grant
- Modes
- speech
- Billing
- Credits
Set it up with your agent
Paste this into Claude Code, Cursor or any coding agent.
Use MAI-Voice-2.1 through TrustedRouter in this project.
1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
https://api.trustedrouter.com/v1 and read the key from
TRUSTEDROUTER_API_KEY.
3. Set the model to microsoft/mai-voice-2.1.
4. Run the tests, then show me the diff before committing.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
with client.audio.speech.with_streaming_response.create(
model="microsoft/mai-voice-2.1",
input="Hello from TrustedRouter.",
voice="en-US-Harper",
response_format="pcm",
) as response:
response.stream_to_file("speech.pcm")
curl https://api.trustedrouter.com/v1/audio/speech \
-H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "microsoft/mai-voice-2.1", "input": "Hello from TrustedRouter.", "voice": "en-US-Harper"}' \
--output speech.pcm
Providers
Audio requests use the listed model and provider. These routes do not silently switch models or providers. Open a row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.
| Provider | Price | Output | Details |
|---|---|---|---|
|
|
$23.21/M characters | Included | |
|
Retention Retention unverified - not strict ZDR: This exact model and upstream ID have not been approved for strict ZDR under the current account controls. Provider-wide ZDR, no-training and successful inference are insufficient. Safety retention or other content storage may apply; the route is excluded until reviewed. This exact model and upstream ID have not been approved for strict ZDR under the current account controls. Provider-wide ZDR, no-training and successful inference are insufficient. Safety retention or other content storage may apply; the route is excluded until reviewed. Location Operator country: US Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Weight format Unknown Price and speed Input $23.21/M characters · Cached input Not applicable · Output Included TTFT: insufficient data Speed: insufficient data |
|||
How to use Microsoft: MAI-Voice-2.1
Text-to-speech, billed per input character, not per token.
- Input
- POST /v1/audio/speech with model, input (text), voice, and response_format.
- Output
- Raw audio bytes. Errors are JSON. See supported response_formats.
Example input
{"model":"microsoft/mai-voice-2.1","input":"Hello!","voice":"en-US-Harper","response_format":"pcm"}
Example output
Binary audio, not a JSON envelope.
Questions
What model ID should I use for MAI-Voice-2.1?
Use microsoft/mai-voice-2.1 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Do you log my prompts or outputs?
No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.
Which providers serve MAI-Voice-2.1?
TrustedRouter currently lists Microsoft Azure AI Foundry for MAI-Voice-2.1. Provider availability and routing eligibility can change as catalog and health data update.
How much does MAI-Voice-2.1 cost through TrustedRouter?
The current Credits price is $23.21/M characters. Output is included; these are audio prices, not text-token prices.
How do I require zero data retention for MAI-Voice-2.1?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.
MAI-Voice-2.1 vs other models
Start building with MAI-Voice-2.1.
No card required. Start with 1 million free tokens.